Summary of the invention
To overcome the problems in correlation technique, the disclosure provides a kind of object monitor method and device.
According to the first aspect of the embodiments of the present disclosure, a kind of object monitor method is provided, comprising:
When there are the sounding reasons for when target sound, judging the target sound in collected sound；
Sounding information is pushed to mobile terminal, the sounding information carries the sounding reason.
In one embodiment, after the push sounding information to mobile terminal, the method also includes:
Receive the video acquisition instruction that the mobile terminal is sent；
It is instructed according to the video acquisition to the mobile terminal pushing video information, so that the mobile terminal shows instituteState video information.
In one embodiment, it is described according to the video acquisition instruct to the mobile terminal pushing video information itBefore, the method also includes:
Obtain the sounding position of the target sound；
It controls camera and turns to the corresponding direction in the sounding position, and acquire the video information.
In one embodiment, the sounding reason of the judgement target sound, comprising:
Feature extraction is carried out to the target sound, obtains target sound characteristic information；
The target sound characteristic information is matched with the multiple sound patterns prestored, and is obtained according to matching resultThe sounding reason of the target sound, the multiple sound pattern target sound caused by different reasons for identification.
In one embodiment, described that feature extraction is carried out to the target sound, target sound characteristic information is obtained, is wrappedIt includes:
Compression processing is carried out to the target sound, obtains voice compressing information；
Feature extraction is carried out to the voice compressing information, obtains the target sound characteristic information.
In one embodiment, the sounding reason of the judgement target sound, comprising:
The target sound is sent to server；
Receive the sounding reason for the target sound that the server returns.
In one embodiment, the method also includes:
If detecting, the current monitor equipment does not access network, broadcasting packet, so that the mobile terminal shows instituteState the prompt information that current monitor equipment does not access network；
The title and password of the router of the mobile terminal broadcast are received, and sends connection request to the router,To be connected on the router.
In one embodiment, the method also includes:
For each sound pattern, current sound template is trained.
It is in one embodiment, described that current sound template is trained, comprising:
Acquire the target sound feature samples of preset quantity；
The target sound feature samples of the preset quantity are inputted into current sound template, obtain the mesh of the preset quantityDistortion distance of the sound characteristic sample relative to current sound template is marked, the distortion distance is for indicating the preset quantityGap between target sound feature samples and the target sound for passing through current sound template output；
If the distortion distance is less than pre-determined distance, stopping is trained the current sound template；
If the distortion distance is more than or equal to pre-determined distance, continue to be trained the current sound template, untilThe distortion distance is less than pre-determined distance.
In one embodiment, the sounding information also carries the target sound.
According to the second aspect of an embodiment of the present disclosure, a kind of object monitor device is provided, comprising:
Judgment module is configured as when, there are when target sound, judging the hair of the target sound in collected soundSound reason；
First pushing module is configured as pushing sounding information to mobile terminal, and the sounding information, which carries, described to be sentencedThe sounding reason that disconnected module is judged.
In one embodiment, described device further include:
Receiving module is configured as after first pushing module pushes sounding information to mobile terminal, receives instituteState the video acquisition instruction of mobile terminal transmission；
Second pushing module is configured as being instructed according to the received video acquisition of the receiving module to the movementTerminal pushing video information, so that the mobile terminal shows the video information.
In one embodiment, described device further include:
Module is obtained, is configured as being instructed according to the video acquisition to the mobile terminal in second pushing moduleBefore pushing video information, the sounding position of the target sound is obtained；
Acquisition module is turned to, being configured as control camera, to turn to the sounding position that the acquisition module obtains correspondingDirection, and acquire the video information.
In one embodiment, the judgment module includes:
Extracting sub-module is configured as carrying out feature extraction to the target sound, obtains target sound characteristic information；
Matched sub-block, is configured as the target sound characteristic information for extracting the extracting sub-module and prestoresMultiple sound patterns matched, and the sounding reason of the target sound, the multiple sound are obtained according to matching resultTemplate target sound caused by different reasons for identification.
In one embodiment, the extracting sub-module includes:
Compression unit is configured as carrying out compression processing to the target sound, obtains voice compressing information；
Extraction unit is configured as the voice compressing information obtained to the compression unit and carries out feature extraction, obtainsTo the target sound characteristic information.
In one embodiment, the judgment module includes:
Sending submodule is configured as sending the target sound to server；
Receiving submodule is configured as receiving the sounding reason for the target sound that the server returns.
In one embodiment, described device further include:
Broadcast module is detected, if being configured as detecting, the current monitor equipment does not access network, broadcasting packet, withThe mobile terminal is set to show that the current monitor equipment does not access the prompt information of network；
Link block is received, is configured as receiving the title and password of the router of the mobile terminal broadcast, and to instituteIt states router and sends connection request, to be connected on the router.
In one embodiment, described device further include:
Training module is configured as being trained current sound template for each sound pattern.
In one embodiment, the training module includes:
Submodule is acquired, the target sound feature samples of acquisition preset quantity are configured as；
Input submodule is configured as the target sound feature of the acquisition collected preset quantity of submoduleSample inputs current sound template, obtains mistake of the target sound feature samples of the preset quantity relative to current sound templateTrue distance, the distortion distance are used to indicate the target sound feature samples of the preset quantity and by the current sound mouldsGap between the target sound of plate output；
First training submodule, if be configured as the distortion distance that the input submodule obtains be less than it is default away fromFrom then stopping is trained the current sound template；
Second training submodule is preset if being configured as the distortion distance that the input submodule obtains and being more than or equal toDistance then continues that the training module is called to be trained the current sound template, until the distortion distance is less than in advanceIf distance.
In one embodiment, the sounding information also carries the target sound.
According to the third aspect of an embodiment of the present disclosure, a kind of object monitor device is provided, comprising:
Processor；
Memory for storage processor executable instruction；
Wherein, processor is configured as:
When there are the sounding reasons for when target sound, judging the target sound in collected sound；
Sounding information is pushed to mobile terminal, the sounding information carries the sounding reason.
The technical scheme provided by this disclosed embodiment can include the following benefits: by judging collected targetThe sounding reason of sound, and the sounding information for carrying sounding reason is pushed to mobile terminal, user is obtained and is supervisedThe sounding reason for controlling object reaches monitoring purpose well.
By allowing mobile terminal to show the video information to mobile terminal pushing video information, to facilitate useThe video information is remotely checked at family.
Video information is acquired by obtaining the sounding position of target sound, implementation is simple.
Pass through the target sound characteristic information that will be extracted and the trained multiple sound patterns progress prestoredMatch, obtain the sounding reason of target sound, implementation is simple, and obtained sounding reason accuracy rate is high.
By to target sound carry out compression processing, reach reduction system operation and storage burden and removal target soundThe purpose of sound correlation.
It also may determine that the sounding reason of target sound by interacting with server, it can be seen that, it can be by moreKind mode judges the sounding reason of target sound.
By interacting with mobile terminal with couple in router, so that establishing binding relationship for the two provides condition, intoIt and is subsequent to be monitored the condition of offer.
By being trained to sound pattern, to judge that the sounding reason of target sound provides condition.
By the way that the target sound feature samples of preset quantity are inputted current sound template, distortion distance is obtained, and will loseTrue distance is compared with pre-determined distance, and to complete the training process of sound pattern, implementation is simple, the sound mould trainedPlate can accurately identify the sounding reason of target sound.
Target sound is also carried by describing sounding information, illustrates the multiplicity of the sounding information pushed to mobile terminalProperty.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, notThe disclosure can be limited.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related toWhen attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodimentDescribed in embodiment do not represent all embodiments consistented with the present invention.On the contrary, they be only with it is such as appendedThe example of device and method being described in detail in claims, some aspects of the invention are consistent.
Fig. 1 is a kind of flow chart of object monitor method shown according to an exemplary embodiment, as shown in Figure 1, this is rightAs monitoring method can be applied in monitoring device, which may include but is not limited to intelligent camera, this method packetInclude following steps S101-S102:
In step s101, when there are the sounding reasons for when target sound, judging the target sound in collected sound.
Wherein it is possible to acquire the sound of monitored object by the microphone being built in video camera, monitored object canTo include but is not limited to children, old man etc., target sound can refer to crying etc..
In this embodiment, intelligent camera, can be special by extracting crying after collecting target sound such as cryingReference breath, and the crying characteristic information of extraction is matched with trained multiple sound patterns to obtain the hair of cryingSound reason.
In addition, intelligent camera can also by with server interact to obtain crying sounding reason.For example, intelligenceEnergy video camera can send target sound to server, and server can also pass through after receiving target sound extracts crying spyReference breath, and the crying characteristic information of extraction is matched with trained multiple sound patterns to obtain the hair of cryingThen sound reason returns to the sounding reason of crying to intelligent camera.
In step s 102, sounding information is pushed to mobile terminal, sounding information carries sounding reason.
In this embodiment, it after judging the sounding reason of target sound, can be pushed to mobile terminal such as mobile phoneCarry the sounding information of sounding reason, with prompt user children cry the reason of.
In addition, target sound can also be carried in the sounding information, for example, can be pushed to mobile phone children crying andThe reason of sobbing.
Above-mentioned object monitor embodiment of the method, by judging the sounding reason of collected target sound, and eventually to movementEnd push carries the sounding information of sounding reason, allows user to obtain the sounding reason of monitored object, reaches fineMonitoring purpose.
Fig. 2 is the flow chart of another object monitor method shown according to an exemplary embodiment, as shown in Fig. 2,After above-mentioned steps S102, this method can also include the following steps:
In step s 103, the video acquisition instruction that mobile terminal is sent is received.
In this embodiment, current monitor equipment be for example built-in with the intelligent camera of Wireless Fidelity (WIFI) chip toAfter mobile terminal pushes sounding information, if the user desired that checking the video information of monitored object, such as the video of childrenInformation then can send video acquisition instruction to intelligent camera by the application program (APP) on mobile terminal.
In this embodiment, intelligent camera and above-mentioned APP can establish binding relationship by same user account.AndThe two is established before binding relationship, and intelligent camera can be linked on same router with the mobile terminal, intelligent cameraThe process of couple in router can be with are as follows:
Intelligent camera, which detects, oneself does not access network, then broadcasting packet, so that mobile terminal shows intelligent cameraThe prompt information of network is not accessed, and user can broadcast by mobile terminal to intelligent camera after seeing the prompt informationThe title and password of the router oneself connected, intelligent camera is after the title and password for receiving router, Ke YixiangThe router sends connection request, to be connected on the router.
It is located in same local area network since intelligent camera and mobile terminal are connected to same router, APP canTo obtain the binding state of intelligent camera by scanning, and show the binding state of intelligent camera.Wherein, binding state packetIt includes and has bound and unbound two states.
When the binding state of intelligent camera is unbound, if user wants to control the intelligent camera, can touchBindings are sent out, then the APP sends the mark and user account such as millet account for carrying intelligent camera to serverRequest, in this way, server can bind intelligent camera and user account according to the request.
After the intelligent camera and mobile terminal APP are bound by same user account, user can pass through the movementTerminal APP sends control instruction such as video acquisition to intelligent camera and instructs.
It in step S104, is instructed according to the video acquisition to mobile terminal pushing video information, so that mobile terminal is aobviousShow video information.
In this embodiment, the sounding position of the available target sound of intelligent camera, and control camera and turn to hairThe corresponding direction in sound position, then acquires video information.The video information acquisition mode is simple, it is easy to accomplish.
After intelligent camera is collected video information, if receiving the video acquisition instruction from mobile terminal,It can be to the mobile terminal pushing video information, to facilitate user remotely to check the video information of monitored object such as children.
The disclosure is illustrated below with reference to Fig. 3, as shown in figure 3, intelligent camera 31 passes through built-in wheatGram wind collects in sound there are after crying, by extracting crying characteristic information, and by the crying characteristic information of extraction withTrained multiple sound patterns are matched to obtain the sounding reason of crying.Since intelligent camera 31 and mobile phone 32 connectIt is located in same local area network to same router 33, therefore, intelligent camera 31 can pass through with the APP being located in mobile phone 32Active user's account establishes binding relationship, therefore intelligent camera 31 can push sounding information to mobile phone 32 by server 34,The sounding information carries the sounding reason of crying, if user wishes to check the video information that intelligent camera 31 is shot at this time,Then video acquisition instruction can be sent to intelligent camera 31 by mobile phone 32, intelligent camera 31 is receiving the video acquisitionAfter instruction, the video information obtained can be pushed to mobile phone 32, user is allowed remotely to check video information.
Above-described embodiment, by allowing mobile terminal to show the video information to mobile terminal pushing video information,To facilitate user remotely to check the video information.
Fig. 4 is a kind of flow chart of sounding reason for judging target sound shown according to an exemplary embodiment, the realityApply example to be described from monitoring device such as intelligent camera pusher side, can also be described from server side, i.e., monitoring device andServer can be judged by the following manner the sounding reason of target sound, as shown in figure 4, this method comprises the following steps:
In step S401, for each sound pattern, current sound template is trained.
In this embodiment, it is necessary first to each sound pattern in multiple sound patterns is trained, with reach byAfter target sound inputs sound pattern, sounding reason can be identified.Wherein, multiple sound patterns for identification draw by different reasonsThe target sound risen.
Wherein, as shown in figure 5, the process being trained to current sound template may include steps of:
In step S4011, the target sound feature samples of preset quantity are acquired.
In step S4012, the target sound feature samples of preset quantity are inputted into current sound template, obtain present countDistortion distance of the target sound feature samples of amount relative to current sound template.
Distortion distance is used to indicate the target sound feature samples of preset quantity and the mesh exported by current sound templateMark the gap between sound.
In step S4013, judge whether distortion distance is less than pre-determined distance, if distortion distance is less than pre-determined distance,Stopping is trained current sound template, if distortion distance is more than or equal to pre-determined distance, turns to and executes step S4011.
Wherein, distortion distance is smaller, then shows the target sound feature samples of preset quantity and by current sound templateGap between the target sound of output is smaller.
When distortion distance is less than pre-determined distance, then otherwise training of the completion to current sound template continues to train, untilDistortion distance is less than pre-determined distance.
In step S402, feature extraction is carried out to target sound, obtains target sound characteristic information.
In this embodiment, if target sound such as crying data volume is bigger, first target sound can be pressedContracting processing, to reduce the operation and storage burden of system, in addition, compressed target sound can remove the correlation of target soundProperty, such as the correlation of removal crying, to achieve the purpose that express crying signal with less characteristic information.Certainly, if meshMark voice data amount is little and has removed correlation, then does not need to carry out compression processing.Wherein it is possible to using existing compression skillArt such as lossless compressiong carries out compression processing to target sound.
In this embodiment, to target sound carry out compression processing can be to compression after obtaining voice compressing informationAcoustic information carries out feature extraction, obtains target sound characteristic information.
In step S403, target sound characteristic information is matched with the multiple sound patterns prestored, and according toThe sounding reason of target sound is obtained with result.
In this embodiment it is possible to by the target sound characteristic information extracted and the trained multiple sound prestoredSound template is matched, to obtain the sounding reason of target sound.
Above-described embodiment passes through the target sound characteristic information that will be extracted and the trained multiple sound prestoredTemplate is matched, and the sounding reason of target sound is obtained, and implementation is simple, and obtained sounding reason accuracy rate is high.
Corresponding with aforementioned object monitoring method embodiment, the disclosure additionally provides object monitor Installation practice.
Fig. 6 is a kind of block diagram of object monitor device shown according to an exemplary embodiment, as shown in fig. 6, the objectMonitoring device includes: judgment module 61 and the first pushing module 62.
Judgment module 61 is configured as when there are the sounding originals for when target sound, judging target sound in collected soundCause.
Wherein, judgment module 61 can acquire the sound of monitored object, quilt by the microphone being built in video cameraMonitored object may include but be not limited to children, old man etc., and target sound can refer to crying etc..
In this embodiment, intelligent camera, can be special by extracting crying after collecting target sound such as cryingReference breath, and the crying characteristic information of extraction is matched with trained multiple sound patterns to obtain the hair of cryingSound reason.
In addition, intelligent camera can also by with server interact to obtain crying sounding reason.For example, intelligenceEnergy video camera can send target sound to server, and server can also pass through after receiving target sound extracts crying spyReference breath, and the crying characteristic information of extraction is matched with trained multiple sound patterns to obtain the hair of cryingThen sound reason returns to the sounding reason of crying to intelligent camera.
First pushing module 62 is configured as pushing sounding information to mobile terminal, and sounding information carries judgment module 61The sounding reason judged.
In this embodiment, it after judging the sounding reason of target sound, can be pushed to mobile terminal such as mobile phoneCarry the sounding information of sounding reason, with prompt user children cry the reason of.
In addition, target sound can also be carried in the sounding information, for example, can be pushed to mobile phone children crying andThe reason of sobbing.
For device as shown in FIG. 6 for realizing above-mentioned method flow as shown in Figure 1, the related content being related to describes phaseTogether, it does not repeat herein.
Above-described embodiment is carried by judging the sounding reason of collected target sound, and to mobile terminal pushThe sounding information of sounding reason allows user to obtain the sounding reason of monitored object, reaches monitoring purpose well.
Fig. 7 is the block diagram of another object monitor device shown according to an exemplary embodiment, as shown in fig. 7, upperOn the basis of stating embodiment illustrated in fig. 6, which may also include that receiving module 63 and the second pushing module 64.
Receiving module 63 is configured as after the first pushing module 62 pushes sounding information to mobile terminal, is received and is movedThe video acquisition instruction that dynamic terminal is sent.
In this embodiment, current monitor equipment be for example built-in with the intelligent camera of Wireless Fidelity (WIFI) chip toAfter mobile terminal pushes sounding information, if the user desired that checking the video information of monitored object, such as the video of childrenInformation then can send video acquisition instruction to intelligent camera by the application program (APP) on mobile terminal.
After the intelligent camera and mobile terminal APP are bound by same user account, user can pass through the movementTerminal APP sends control instruction such as video acquisition to intelligent camera and instructs.
Second pushing module 64 is configured as being instructed according to the received video acquisition of receiving module 63 to mobile terminal pushVideo information, so that mobile terminal shows video information.
For device as shown in Figure 7 for realizing above-mentioned method flow as shown in Figure 2, the related content being related to describes phaseTogether, it does not repeat herein.
Above-described embodiment, by allowing mobile terminal to show the video information to mobile terminal pushing video information,To facilitate user remotely to check the video information.
Fig. 8 is the block diagram of another object monitor device shown according to an exemplary embodiment, as shown in figure 8, upperOn the basis of stating embodiment illustrated in fig. 7, which can also include: to obtain module 65 and steering acquisition module 66.
Module 65 is obtained to be configured as being instructed according to video acquisition to mobile terminal pushing video in the second pushing module 64Before information, the sounding position of target sound is obtained.
It turns to acquisition module 66 and is configured as the corresponding side in sounding position that control camera turns to the acquisition acquisition of module 65To, and acquire video information.
In this embodiment, the sounding position of the available target sound of intelligent camera, and control camera and turn to hairThe corresponding direction in sound position, then acquires video information.The video information acquisition mode is simple, it is easy to accomplish.
For device as shown in Figure 8 for realizing above-mentioned method flow as shown in Figure 2, the related content being related to describes phaseTogether, it does not repeat herein.
Above-described embodiment acquires video information by obtaining the sounding position of target sound, and implementation is simple.
Fig. 9 is the block diagram of another object monitor device shown according to an exemplary embodiment, as shown in figure 9, upperOn the basis of stating embodiment illustrated in fig. 6, judgment module 61 can include: extracting sub-module 611 and matched sub-block 612.
Extracting sub-module 611 is configured as carrying out feature extraction to target sound, obtains target sound characteristic information.
Matched sub-block 612 be configured as by target sound characteristic information that extracting sub-module 611 is extracted with prestoreMultiple sound patterns are matched, and obtain the sounding reason of target sound according to matching result, and multiple sound patterns are for knowingTarget sound caused by not different reasons.
In this embodiment it is possible to by the target sound characteristic information extracted and the trained multiple sound prestoredSound template is matched, to obtain the sounding reason of target sound.
For device as shown in Figure 9 for realizing above-mentioned method flow as shown in Figure 4, the related content being related to describes phaseTogether, it does not repeat herein.
Above-described embodiment passes through the target sound characteristic information that will be extracted and the trained multiple sound prestoredTemplate is matched, and the sounding reason of target sound is obtained, and implementation is simple, and obtained sounding reason accuracy rate is high.
Figure 10 is the block diagram of another object monitor device shown according to an exemplary embodiment, as shown in Figure 10,On the basis of above-mentioned embodiment illustrated in fig. 9, extracting sub-module 611 can include: compression unit 6111 and extraction unit 6112.
Compression unit 6111 is configured as carrying out compression processing to target sound, obtains voice compressing information.
Extraction unit 6112 is configured as the voice compressing information obtained to compression unit 6111 and carries out feature extraction, obtainsTarget sound characteristic information.
For realizing above-mentioned method flow as shown in Figure 4, the related content being related to is described device as shown in Figure 10It is identical, it does not repeat herein.
In this embodiment, if target sound such as crying data volume is bigger, first target sound can be pressedContracting processing, to reduce the operation and storage burden of system, in addition, compressed target sound can remove the correlation of target soundProperty, such as the correlation of removal crying, to achieve the purpose that express crying signal with less characteristic information.Certainly, if meshMark voice data amount is little and has removed correlation, then does not need to carry out compression processing.Wherein it is possible to using existing compression skillArt such as lossless compressiong carries out compression processing to target sound.
Above-described embodiment, by target sound carry out compression processing, reach operation and the storage burden of reduction system withAnd the purpose of removal target sound correlation.
Figure 11 is the block diagram of another object monitor device shown according to an exemplary embodiment, as shown in figure 11,On the basis of above-mentioned embodiment illustrated in fig. 6, judgment module 61 can include: sending submodule 613 and receiving submodule 614.
Sending submodule 613 is configured as sending target sound to server.
Receiving submodule 614 is configured as receiving the sounding reason for the target sound that server returns.
Object monitor device such as intelligent camera can be former by the sounding for interacting to obtain crying with serverCause.For example, intelligent camera can send target sound to server, server can also pass through after receiving target soundCrying characteristic information is extracted, and the crying characteristic information of extraction is matched to come with trained multiple sound patternsTo the sounding reason of crying, the sounding reason of crying is then returned to intelligent camera.
For realizing above-mentioned method flow as shown in Figure 1, the related content being related to is described device as shown in figure 11It is identical, it does not repeat herein.
Above-described embodiment also may determine that the sounding reason of target sound by interacting with server, it can be seen that,The sounding reason of target sound can be judged in several ways.
Figure 12 is the block diagram of another object monitor device shown according to an exemplary embodiment, as shown in figure 12,On the basis of above-mentioned embodiment illustrated in fig. 7, which may also include that detection broadcast module 67 and receives link block 68.
If detection broadcast module 67 is configured as detecting current monitor equipment and does not access network, broadcasting packet, so thatMobile terminal shows that current monitor equipment does not access the prompt information of network.
It receives link block 68 to be configured as receiving the title and password of the router of mobile terminal broadcast, and to routerConnection request is sent, to be connected on router.
In this embodiment, intelligent camera and above-mentioned APP can establish binding relationship by same user account.AndThe two is established before binding relationship, and intelligent camera can be linked on same router with the mobile terminal, intelligent cameraThe process of couple in router can be with are as follows:
Intelligent camera, which detects, oneself does not access network, then broadcasting packet, so that mobile terminal shows intelligent cameraThe prompt information of network is not accessed, and user can broadcast by mobile terminal to intelligent camera after seeing the prompt informationThe title and password of the router oneself connected, intelligent camera is after the title and password for receiving router, Ke YixiangThe router sends connection request, to be connected on the router.
It is located in same local area network since intelligent camera and mobile terminal are connected to same router, APP canTo obtain the binding state of intelligent camera by scanning, and show the binding state of intelligent camera.Wherein, binding state packetIt includes and has bound and unbound two states.
When the binding state of intelligent camera is unbound, if user wants to control the intelligent camera, can touchBindings are sent out, then the APP sends the mark and user account such as millet account for carrying intelligent camera to serverRequest, in this way, server can bind intelligent camera and user account according to the request.
For realizing above-mentioned method flow as shown in Figure 2, the related content being related to is described device as shown in figure 12It is identical, it does not repeat herein.
Above-described embodiment, by interacting with mobile terminal with couple in router, to establish binding relationship for the twoOffer condition, and then the condition of offer is monitored to be subsequent.
Figure 13 is the block diagram of another object monitor device shown according to an exemplary embodiment, as shown in figure 13,On the basis of above-mentioned embodiment illustrated in fig. 9, which may also include that training module 69.
Training module 69 is configured as being trained current sound template for each sound pattern.
In this embodiment, it is necessary first to each sound pattern in multiple sound patterns is trained, with reach byAfter target sound inputs sound pattern, sounding reason can be identified.Wherein, multiple sound patterns for identification draw by different reasonsThe target sound risen.
For realizing above-mentioned method flow as shown in Figure 4, the related content being related to describes device as shown in fig. 13 thatIt is identical, it does not repeat herein.
Above-described embodiment, by being trained to sound pattern, to judge that the sounding reason of target sound provides condition.
Figure 14 is the block diagram of another object monitor device shown according to an exemplary embodiment, as shown in figure 14,On the basis of above-mentioned embodiment illustrated in fig. 13, training module 69 can include: acquisition submodule 691, input submodule 692, firstTraining submodule 693 and the second training submodule 694.
Acquisition submodule 691 is configured as the target sound feature samples of acquisition preset quantity.
Input submodule 692 is configured as that the target sound feature sample of the collected preset quantity of submodule 691 will be acquiredThis input current sound template, obtain the target sound feature samples of preset quantity relative to current sound template distortion away fromFrom distortion distance is used to indicate the target sound feature samples of preset quantity and the target sound exported by current sound templateBetween gap.
If the first training submodule 693, which is configured as the distortion distance that input submodule 692 obtains, is less than pre-determined distance,Stopping is trained current sound template.
If the second training submodule 694 be configured as distortion distance that input submodule 692 obtains be more than or equal to it is default away fromFrom, then continue call training module current sound template is trained, until distortion distance be less than pre-determined distance.
Wherein, distortion distance is smaller, then shows the target sound feature samples of preset quantity and by current sound templateGap between the target sound of output is smaller.
When distortion distance is less than pre-determined distance, then otherwise training of the completion to current sound template continues to train, untilDistortion distance is less than pre-determined distance.
For realizing above-mentioned method flow as shown in Figure 5, the related content being related to is described device as shown in figure 14It is identical, it does not repeat herein.
Above-described embodiment is distorted by the way that the target sound feature samples of preset quantity are inputted current sound templateDistance, and distortion distance is compared with pre-determined distance, to complete the training process of sound pattern, implementation is simple, instructionThe sound pattern practised can accurately identify the sounding reason of target sound.
About the device in above-described embodiment, the concrete mode that wherein modules, submodule execute operation is havingIt closes and is described in detail in the embodiment of this method, no detailed explanation will be given here.
Figure 15 is a kind of block diagram suitable for object monitor device shown according to an exemplary embodiment.For example, device1500 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical treatmentEquipment, body-building equipment, personal digital assistant, aircraft etc..
Referring to Fig.1 5, device 1500 may include following one or more components: processing component 1502, memory 1504,Power supply module 1506, multimedia component 1508, audio component 1510, the interface 1512 of input/output (I/O), sensor module1514 and communication component 1516.
The integrated operation of the usual control device 1500 of processing component 1502, such as with display, telephone call, data communication,Camera operation and record operate associated operation.Processing element 1502 may include one or more processors 1520 to executeInstruction, to perform all or part of the steps of the methods described above.In addition, processing component 1502 may include one or more mouldsBlock, convenient for the interaction between processing component 1502 and other assemblies.For example, processing component 1502 may include multi-media module,To facilitate the interaction between multimedia component 1508 and processing component 1502.
Memory 1504 is configured as storing various types of data to support the operation in equipment 1500.These dataExample includes the instruction of any application or method for operating on device 1500, contact data, telephone book data,Message, picture, video etc..Memory 1504 can by any kind of volatibility or non-volatile memory device or theyCombination is realized, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), it is erasable canProgram read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memoryReservoir, disk or CD.
Power supply module 1506 provides electric power for the various assemblies of device 1500.Power supply module 1506 may include power managementSystem, one or more power supplys and other with for device 1500 generate, manage, and distribute the associated component of electric power.
Multimedia component 1508 includes the screen of one output interface of offer between described device 1500 and user.?In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel,Screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes that one or more touch passesSensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding is dynamicThe boundary of work, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, moreMedia component 1508 includes a front camera and/or rear camera.When equipment 1500 is in operation mode, as shot mouldWhen formula or video mode, front camera and/or rear camera can receive external multi-medium data.Each preposition camera shootingHead and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 1510 is configured as output and/or input audio signal.For example, audio component 1510 includes a wheatGram wind (MIC), when device 1500 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone quiltIt is configured to receive external audio signal.The received audio signal can be further stored in memory 1504 or via communicationComponent 1516 is sent.In some embodiments, audio component 1510 further includes a loudspeaker, is used for output audio signal.
I/O interface 1512 provides interface, above-mentioned peripheral interface module between processing component 1502 and peripheral interface moduleIt can be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button andLocking press button.
Sensor module 1514 includes one or more sensors, and the state for providing various aspects for device 1500 is commentedEstimate.For example, sensor module 1514 can detecte the state that opens/closes of equipment 1500, the relative positioning of component, such as instituteThe display and keypad that component is device 1500 are stated, sensor module 1514 can be with detection device 1500 or device 1,500 1The position change of a component, the existence or non-existence that user contacts with device 1500,1500 orientation of device or acceleration/deceleration and dressSet 1500 temperature change.Sensor module 1514 may include proximity sensor, be configured in not any physicsIt is detected the presence of nearby objects when contact.Sensor module 1514 can also include optical sensor, as CMOS or ccd image are sensedDevice, for being used in imaging applications.In some embodiments, which can also include acceleration sensingDevice, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 1516 is configured to facilitate the communication of wired or wireless way between device 1500 and other equipment.DressThe wireless network based on communication standard, such as WiFi can be accessed by setting 1500,2G or 3G or their combination.It is exemplary at oneIn embodiment, communication component 1516 receives broadcast singal or broadcast correlation from external broadcasting management system via broadcast channelInformation.In one exemplary embodiment, the communication component 1516 further includes near-field communication (NFC) module, to promote short distanceCommunication.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band can be based in NFC module(UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 1500 can be by one or more application specific integrated circuit (ASIC), numberSignal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally providedIt such as include the memory 1504 of instruction, above-metioned instruction can be executed by the processor 1520 of device 1500 to complete the above method.ExampleSuch as, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, softDisk and optical data storage devices etc..
Those skilled in the art will readily occur to its of the disclosure after considering specification and practicing disclosure disclosed hereinIts embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes orPerson's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosureOr conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by followingClaim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, andAnd various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.